官方服务：
资源简介：
Cases for Benchmark (selected by myself) in Agent_Benchmark
应用场景：
创建时间：
2026-03-26
相关数据集
OpenHandsCommunity/SWE-bench-devin-full-filtered
--- license: mit dataset_info: features: - name: repo dtype: string - name: instance_id dtype: string - name: base_commit dtype: string - name: patch dtype: string - name:
Hugging Face2024-04-09 更新80
DCAgent2/swebench_verified_random_100_folders_rl__24GPU_base__exp_rpt_stack_bash__Qwen3_6733ce81
--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: agent dtype: string - name: model dtype
Hugging Face2026-03-21 更新50
DCAgent2/swebench_verified_random_100_folders_SweSmith_8B_SFT_Rope_step62_20260323_183107
--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: agent dtype: string - name: model dtype
Hugging Face2026-03-24 更新50
DCAgent2/swebench_verified_random_100_folders_a1_issue_tasks_20260325_083244
--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: agent dtype: string - name: model dtype
Hugging Face2026-03-25 更新60
DCAgent2/swebench_verified_random_100_folders_a1_nemotron_pytest_20260326_090151
--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: agent dtype: string - name: model dtype
Hugging Face2026-03-27 更新50
